HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models

arXiv:2404.19065v1 Announce Type: cross
Abstract: Recent research on instructable agents has used memory-augmented Large Language Models (LLMs) as task planners, a technique that retrieves language-program examples relevant to the input instruction and uses them as in-context examples in the LLM prompt to improve the performance of the LLM in inferring the correct action and task plans. In this technical report, we extend the capabilities of HELPER, by expanding its memory with a wider array of examples and prompts, and by …

abstract agent agents arxiv context cs.ai cs.cl cs.cv cs.lg domains embodied examples interactive language language models large language large language models llm llm prompt llms memory prompt research them type vision vision-language